report

A report showing trends in dollars spent for each one percent of weekly usage across Claude, Codex, or both.

In plain words
What is it for?
Use it to review Claude subscription-week trends, Codex quota windows, or separate reports for both providers.
Why use it?
It helps compare spending against usage over time, while marking costs unavailable when the supporting usage or quota evidence is insufficient.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/omrikais/cctally/report
Clone the repo
git clone --depth 1 https://github.com/omrikais/cctally
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,119 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02119
Opus 5 $0.00000 $0.01059
Sonnet 5 $0.00000 $0.00424
Haiku 4.5 $0.00000 $0.00212

Measured 2d ago against content hash b3041a56b047, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

report scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/commands/report.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

report

Trend table of dollars per 1% weekly usage. The headline command of this project.

Claude cost coverage: Claude dollar and token totals are transcript-derived lower bounds, not exact /usage billing totals. Codex accounting is unaffected.

Provider-aware report routing

cctally report and cctally report --source claude preserve the existing Claude subscription-week trend. The flat command also accepts --source {claude,codex,all} (default claude); cctally claude report and cctally codex report are fixed-source forms and do not accept --source.

Codex report is quota-window-native, not a calendar or Claude subscription week report. It emits one source/root/logical-limit series, using each selected native reset block's [reset - window, min(as-of, reset)) accounting interval. The --weeks N value selects the newest N S2 reset blocks within every logical limit series, including the current block. Cost per percent is null/unavailable when the selected percent or quota/cost evidence is insufficient; it is never fabricated as zero.

--source all keeps Claude subscription-week rows and every Codex logical-limit series in separate source sections. It has no combined trend, average, USD, token total, used percent, reset, or dollars-per-percent field: one Codex accounting interval can overlap multiple logical limits, so adding per-limit series would double count physical usage. That refusal is specifically about overlapping logical-limit series, not about combining providers as such: the dashboard does publish a combined USD figure over one shared absolute range for its cross-provider rankings, which carry no per-limit series to overlap. --speed applies to Codex/all; --week-start-name, --mode, --offline, and --project are Claude-only options (they affect only the Claude leg of all); --detail remains source-native in both sections.

The fixed cctally codex report parser accepts only its native surface: it does not expose the Claude-only --week-start-name, --mode, --offline, or --project flags. Its --sync-current syncs Codex accounting and reconciles native quota state; it does not invoke sync-week.

Read the full file on GitHub · 151 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 151 lines · 0 tokens per session scan A b3041a56b047

Subscribe to this mod's changes

report is a command published in the GitHub repository omrikais/cctally (5 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,119 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.